Ad Creative
LeoYeAI/openclaw-marketing-skills
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform.
Plan or audit paid ads with current platform rules and benchmarks: Google PMax/AI Max, Meta, retail.
Install Paid Advertising
$ npx skills add indranilbanerjee/digital-marketing-pro --skill paid-advertising -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install indranilbanerjee/digital-marketing-pro paid-advertising --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/indranilbanerjee/digital-marketing-pro.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/paid-advertising .claude/skills/paid-advertising && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "paid-advertising" agent skill from https://github.com/indranilbanerjee/digital-marketing-pro/tree/main/skills/paid-advertising into .claude/skills/paid-advertising/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paid-advertising", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/indranilbanerjee/digital-marketing-pro/tree/main/skills/paid-advertisingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add indranilbanerjee/digital-marketing-pro --skill paid-advertising -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install indranilbanerjee/digital-marketing-pro paid-advertising --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/indranilbanerjee/digital-marketing-pro.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/paid-advertising .agents/skills/paid-advertising && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "paid-advertising" agent skill from https://github.com/indranilbanerjee/digital-marketing-pro/tree/main/skills/paid-advertising into .agents/skills/paid-advertising/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paid-advertising", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add indranilbanerjee/digital-marketing-pro --skill paid-advertising -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install indranilbanerjee/digital-marketing-pro paid-advertising --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/indranilbanerjee/digital-marketing-pro.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/paid-advertising .cursor/skills/paid-advertising && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "paid-advertising" agent skill from https://github.com/indranilbanerjee/digital-marketing-pro/tree/main/skills/paid-advertising into .cursor/skills/paid-advertising/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paid-advertising", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/indranilbanerjee/digital-marketing-pro.git --path skills/paid-advertising--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add indranilbanerjee/digital-marketing-pro --skill paid-advertising -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install indranilbanerjee/digital-marketing-pro paid-advertising --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/indranilbanerjee/digital-marketing-pro.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/paid-advertising .gemini/skills/paid-advertising && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "paid-advertising" agent skill from https://github.com/indranilbanerjee/digital-marketing-pro/tree/main/skills/paid-advertising into .gemini/skills/paid-advertising/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paid-advertising", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install indranilbanerjee/digital-marketing-pro paid-advertisingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add indranilbanerjee/digital-marketing-pro --skill paid-advertising -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/indranilbanerjee/digital-marketing-pro.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/paid-advertising .github/skills/paid-advertising && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "paid-advertising" agent skill from https://github.com/indranilbanerjee/digital-marketing-pro/tree/main/skills/paid-advertising into .github/skills/paid-advertising/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paid-advertising", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add indranilbanerjee/digital-marketing-pro --skill paid-advertising -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install indranilbanerjee/digital-marketing-pro paid-advertising --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/indranilbanerjee/digital-marketing-pro.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/paid-advertising .opencode/skills/paid-advertising && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "paid-advertising" agent skill from https://github.com/indranilbanerjee/digital-marketing-pro/tree/main/skills/paid-advertising into .opencode/skills/paid-advertising/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paid-advertising", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
paid-advertising- GitHub stars
- 862
- Used in
- 1 other repo
- Token cost
- ~5.3k tokens
- SKILL.md length
- 2,499 words
- Files
- 14
- Skills in repo
- 162
- Repo updated
- First seen
- Licence
- MIT
At a glance
Plan or audit paid ads with current platform rules and benchmarks: Google PMax/AI Max, Meta, retail.
- Works in 9 steps: Check session context — The active brand… → If you need the full profile, read:… → Apply brand voice — Formality, energy,… → …
- Tasks that involve Paid advertising
- SKILL.md covers Since August 2026 (verified…, Recent platform API changes…, When to Use This Skill and Brand Context (Auto-Applied), plus 7 more sections
- Calls python
What it does
Paid Advertising is an agent skill from indranilbanerjee/digital-marketing-pro. Plan or audit paid ads with current platform rules and benchmarks: Google PMax/AI Max, Meta, retail. "should we use Performance Max"
Its SKILL.md is about 5.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files (for example `ads-in-ai-answers.md`, `audio-programmatic.md` and `bid-strategy.md`).
It sits in Marketing & SEO, covering Paid advertising. The repository describes itself as: An open-source AI marketing operating system for strategy, SEO, AEO/GEO, paid media, content, CRM, and analytics - grounded in brand context, human approval, and verifiable… The licence is MIT.
When your agent uses it
- Tasks that involve Paid advertising
Example prompts
- “should we use Performance Max”
- “/paid-advertising”
Requirements
- Python 3
Workflow steps
9 steps, taken from the first numbered list in SKILL.md.
- Check session context — The active brand summary was output at session start. Use the brand name, industry, voice settings, channels…
- If you need the full profile, read: ~/.claude-marketing/brands/{slug}/profile.json
- Apply brand voice — Formality, energy, humor, authority levels must shape all content tone and word choices
- Check compliance — Auto-apply rules for brand's target_markets and industry using skills/context-engine/compliance-rules.md
- Reference industry benchmarks — Consult skills/context-engine/industry-profiles.md for the brand's industry
- Use platform specs — Reference skills/context-engine/platform-specs.md for character limits and format requirements
- Check campaign history — Run python "${CLAUDE_PLUGIN_ROOT}/scripts/campaign-tracker.py" --brand {slug} --action list-campaigns before…
- If no brand exists, say: "No brand profile found. Use /digital-marketing-pro:brand-setup to create one, or I can proceed with general best…
- Check brand guidelines — If ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json exists, load and enforce: restrictions.md for…
What it can do on your machine
Read from SKILL.md and the folder at commit 9e949f3. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
blog.googlesupport.google.comlearn.microsoft.comadvertising.amazon.comdevelopers.openai.comdevelopers.google.comads-developers.googleblog.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Paid Advertising loads about 5.3k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 2,499 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from indranilbanerjee/digital-marketing-pro at commit 9e949f3, republished under its MIT licence (© indranilbanerjee). 2,499 words, ~5,304 tokens.
Download SKILL.mdSave it as
.claude/skills/paid-advertising/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.- name
- paid-advertising
- description
- Plan or audit paid ads with current platform rules and benchmarks: Google PMax/AI Max, Meta, retail. "should we use Performance Max"
Paid Advertising
Script location. If your host does not set
${CLAUDE_PLUGIN_ROOT}, the scripts are in this plugin'sscripts/folder, next toskills/.
Since August 2026 (verified 2026-10-04)
Google AI Max auto-upgrade: Search campaigns using automatically created assets or campaign-level broad match auto-upgrade to AI Max starting September 2026; the Dynamic Search Ads (DSA) sunset and its auto-upgrade moved to February 2027. Audit every account for campaigns already flipped, and run the
ADOPT_AI_MAXexperiment on the rest before Google does it for you. Source: blog.google.Google Ads Limited Ad Serving now covers every surface (Search, YouTube, Gmail, Play, Discover), rolling out gradually through 2028 — new advertisers can see throttled delivery while trust builds. Source: Ads policy (posted 5 Aug 2026).
LinkedIn Marketing API:
202608made the Matched Audiences API generally available (cap: 1,000 DMP segments per account), added account-level dynamic UTMs and MQL/SQL conversion types, and sunset legacy geo on 31 Aug 2026;202609added hashed first/last names in the Conversions API and a 180-day attribution window. Versions202510and202511sunset on 15 Oct and 16 Nov 2026 — move integrations to202609. Source: recent changes.Amazon Ads (unBoxed, 30 Sep 2026): an "Amazon Ads Agent" unifying DSP and the Ads Console, Full-Funnel Campaigns, Sponsored Services, and an Amazon Ads MCP Server (Lite) — a connector candidate for retail-media workflows. Source: Amazon Ads news.
ChatGPT Ads — the developer surface is primary-documented (checked 2026-10-04): developers.openai.com/ads documents:
- an Advertiser API and a Bulk API
- a Measurement Pixel and a server-side Conversions API, deduplicated on pixel
event_id= APIid - Custom Audiences from customer lists only, unavailable in the EEA and Switzerland
- Product Feeds plus a Delta Feeds API for price, availability, and title changes
- a Reporting API, with a 30-day click / 1-day view default
- Hotel Feeds (limited beta)
The launch dates, the audience (Free/Go users), the country rollout (31 European markets on 18 Aug, Southeast Asia + Taiwan on 23 Sep) and "Sponsored Agents" remain secondary-sourced: label them "reported, unverified" and confirm availability in the brand's Ads Manager before planning spend. Do not quote CPMs or auction mechanics. Planning, tracking, reporting and feed detail:
ads-in-ai-answers.md.Google AI Mode ads (checked 2026-10-04): there is no separate campaign type. Google says advertisers reach the new AI Mode formats ("Conversational Discovery ads", "Highlighted Answers") by building on AI Max for Search, AI Max for Shopping, and Performance Max.
- Direct Offers (a pilot since January 2026) is expanding to promotion bundling, native checkout for UCP merchants, and travel deals.
- Business Agent for leads (chat inside the ad instead of a form) is due "in the coming months".
- The post gives no AI-Mode-specific measurement, so report at the AI Max / PMax campaign level and don't promise an AI-Mode-only KPI.
Source: blog.google (20 May 2026). Detail:
ads-in-ai-answers.md.
Recent platform API changes (as of July 2026)
Target Google Ads API v24.2 for stable integrations (v24 line supported into 2027). v25 (July 2026) is the new major release with breaking changes: the legacy CustomerLifecycleGoal/CampaignLifecycleGoal resources are removed (migrate to the unified Goal + CampaignGoalConfig schema), plus new loyalty-retention optimization goals, social-engagement metrics for Shorts ads, duration-level breakdowns for non-skippable YouTube inventory, and YouTube third-party conversion attribution. Adopt v25 deliberately, not by default. Full detail — including AI Max — lives in google-ads.md, the single source for the Google Ads API surface. Sources: release notes · v25 announcement.
Meta (Marketing API v25, in effect): standalone Advantage+ Shopping / App campaigns can no longer be created via the API on any version (since 19 May 2026); v26 (Sept 2026) pauses remaining ones — use the unified Advantage+ setup (details in meta-ads.md). The new Page Viewer metric replaces legacy reach (Post/Page Reach, Video Impressions, and Story Impressions retire from the Graph API) — update any reporting that reads those fields. LinkedIn: version 202607 is live (monthly cadence); it adds an automatic "Not Interested" CTA on Message Ads and a SHA256_IP_ADDRESS identifier in the Conversions API.
Highlights that affect campaign construction:
- v24.2 (24 Jun 2026): first-class Local Services Ads support (
AssetGroup.google_local_services_info), landing-page-text auto-generation (AssetAutomationType.GENERATE_LANDING_PAGE_TEXT), and a beta Multi-Party Auth review resource for regulated verticals (finance, health, political). - v24.1 (13 May 2026) — AI Max: four new experiment types (
ADOPT_AI_MAX,ADOPT_BROAD_MATCH_KEYWORDS,OPTIMIZE_ASSETS,PMAX_REPLACEMENT_SHOPPING). Run anADOPT_AI_MAXexperiment before any AI Max rollout — it gives statistically-clean lift numbers vs the baseline. Also addsmobile_device_platform(iOS vs Android) reporting segmentation. - v24.0 (22 Apr 2026) — breaking:
videos+logo_imagesnow REQUIRED onDemandGenVideoResponsiveAdInfo/VideoResponsiveAdInfo(andbusiness_nameon the latter);Campaign.video_brand_safety_suitabilityREMOVED (moved to the Customer level);CallAd/CallAdInfofully removed (use Call Assets). - v23.1 (25 Feb 2026):
text_guidelines.term_exclusions+text_guidelines.messaging_restrictionson AI-generated Performance Max and Search assets — pipe a brand's banned-word list (profile.json → restrictions.md → banned_words) and approved messaging straight into PMax asset-gen guardrails.
When to Use This Skill
Activate this skill when the user's request involves any of the following:
- Creating, auditing, or optimizing campaigns on Google Ads, Meta/Facebook Ads, LinkedIn Ads, or TikTok Ads
- Designing campaign structures, ad groups, or ad set hierarchies on any paid platform
- Selecting or troubleshooting bid strategies (manual CPC, target CPA, target ROAS, maximize conversions, etc.)
- Building audience strategies including prospecting, retargeting, lookalike/similar audiences, or custom audiences
- Allocating or pacing budgets across platforms or campaigns
- Setting up or optimizing Google Shopping, Performance Max, YouTube Ads, or Display campaigns
- Working with Meta Advantage+ campaigns or manual campaign structures
- Running LinkedIn Ads with account-based marketing (ABM) targeting
- Launching TikTok Ads including Spark Ads or TikTok Shop integrations
- Programmatic advertising including DSP selection, connected TV (CTV), or digital out-of-home (DOOH)
- Retail media networks including Amazon Ads, Walmart Connect, Target Roundel, Kroger Precision Marketing, or Instacart Ads
- Running Microsoft Advertising (Bing Ads) campaigns, including Google Ads import and Microsoft Audience Network placements
- Planning native advertising campaigns on content discovery networks (Taboola, Outbrain, Nativo)
- Buying audio or podcast advertising across streaming platforms (Spotify, Pandora/SiriusXM, iHeartRadio) or programmatic audio
- Ads inside AI answers: ChatGPT Ads (planning, Pixel + Conversions API tracking, reporting, product/delta feeds) or reaching Google AI Mode through AI Max and Performance Max
- Any question about paid media strategy, creative strategy for ads, or paid channel mix decisions
Brand Context (Auto-Applied)
Before producing any marketing output from this module:
- Check session context — The active brand summary was output at session start. Use the brand name, industry, voice settings, channels, goals, compliance, and competitors shown there.
- If you need the full profile, read:
~/.claude-marketing/brands/{slug}/profile.json - Apply brand voice — Formality, energy, humor, authority levels must shape all content tone and word choices
- Check compliance — Auto-apply rules for brand's target_markets and industry using
skills/context-engine/compliance-rules.md - Reference industry benchmarks — Consult
skills/context-engine/industry-profiles.mdfor the brand's industry - Use platform specs — Reference
skills/context-engine/platform-specs.mdfor character limits and format requirements - Check campaign history — Run
python "${CLAUDE_PLUGIN_ROOT}/scripts/campaign-tracker.py" --brand {slug} --action list-campaignsbefore planning new work - If no brand exists, say: "No brand profile found. Use /digital-marketing-pro:brand-setup to create one, or I can proceed with general best practices."
- Check brand guidelines — If
~/.claude-marketing/brands/{slug}/guidelines/_manifest.jsonexists, load and enforce:restrictions.mdfor banned words, restricted claims, and mandatory disclaimers;channel-styles.mdfor channel-specific tone overrides (may differ from base voice);messaging.mdfor approved key messages, taglines, and positioning language;voice-and-tone.mdfor detailed voice rules beyond the 4 numeric scores. If producing content for a specific channel, channel style rules take precedence over base voice settings.
Do not ask the user for information that already exists in their brand profile.
Required Context
Before executing, gather the following from the user (ask if not provided):
- Business type: B2B, B2C, D2C, marketplace, local business
- Current platforms: Which ad platforms are active (if any)
- Monthly budget: Total paid media spend or per-platform budgets
- Goals: Primary KPI (ROAS, CPA, CPL, brand awareness, traffic) and target values
- Audience: Who they are trying to reach (demographics, firmographics, interests, behaviors)
- Funnel stage focus: Top-of-funnel awareness, mid-funnel consideration, or bottom-funnel conversion
- Existing assets: Landing pages, creative assets, product feeds, tracking setup
- Tracking infrastructure: Pixel/tag status, conversion tracking, attribution model in use
- Industry: Needed to flag regulated category restrictions (healthcare, finance, alcohol, cannabis, gambling)
Capabilities
Campaign Structure Design
- Platform-specific campaign architecture (campaigns, ad groups/ad sets, ads)
- Naming conventions for scalable account management
- Campaign type selection per objective (Search, Display, Shopping, Video, App, PMax, Demand Gen)
- Ad group theming and keyword/audience segmentation strategies
Audience Strategy
- Prospecting: Interest-based, behavior-based, demographic, and contextual targeting
- Retargeting: Website visitors, video viewers, lead form engagers, customer lists, cart abandoners
- Lookalike/Similar audiences: Source audience selection, expansion percentages, layering strategies
- ABM targeting: Company lists, job title targeting, seniority filtering (LinkedIn-specific)
- Exclusion strategies: Negative audiences, customer suppression, converter exclusion windows
Bid Strategy Selection
- Manual vs automated bidding decision framework
- Target CPA, target ROAS, maximize conversions, maximize conversion value
- Portfolio bid strategies for Google Ads
- Learning phase management and bid strategy transitions
- Seasonality adjustments and bid modifiers
Creative Strategy
- Ad format selection per platform and objective
- Responsive search ads (RSA) best practices and pin strategies
- Meta creative diversification (static, video, carousel, collection, instant experience)
- LinkedIn creative formats (single image, carousel, video, document, conversation ads)
- TikTok native-style creative principles
- Creative testing frameworks (variable isolation, iterative testing)
Show full SKILL.md (1,014 more words)Show less
Budget Allocation and Pacing
- Cross-platform budget distribution models
- Campaign-level budget optimization vs ad-set level budgets
- Daily vs lifetime budgets and when to use each
- Pacing strategies for monthly/quarterly targets
- Budget scaling rules (20% rule for Google, CBO adjustments for Meta)
Platform-Specific Expertise
- Google Ads: Search, Display, Performance Max, YouTube (in-stream, Shorts, Discovery), Shopping, Demand Gen
- Meta Ads: unified Advantage+ campaigns (ASC/AAC legacy formats retiring — see meta-ads.md), manual campaigns, catalog ads, lead gen forms
- LinkedIn Ads: Sponsored Content, Message Ads, Lead Gen Forms, Document Ads, ABM list targeting
- TikTok Ads: In-Feed, TopView, Spark Ads, TikTok Shop product ads, Branded Effects
- Programmatic: DSP selection (DV360, The Trade Desk, Amazon DSP), CTV, DOOH, audio
- Retail Media: Amazon Sponsored Products/Brands/Display, Walmart Connect, Target Roundel, Kroger Precision Marketing, Instacart Ads
Process
Standard Campaign Build (Most Common Use Case)
- Define objectives -- Clarify the primary KPI and success metric. Map to the correct campaign type per platform.
- Audience architecture -- Design the full-funnel audience strategy: cold prospecting segments, warm retargeting pools, and hot remarketing lists. Define exclusions.
- Campaign structure -- Build the campaign hierarchy with naming conventions. Determine budget allocation across campaigns.
- Bid strategy selection -- Choose the appropriate bid strategy based on data maturity, conversion volume, and goals. Reference
bid-strategy.mdfor decision trees. - Creative strategy -- Define ad formats, messaging angles, and creative variations. Map creative to funnel stage and audience segment.
- Tracking validation -- Confirm pixel/tag setup, conversion actions, and attribution model before launch.
- Launch plan -- Set launch budgets (often lower than steady-state), define learning phase expectations, and establish the first optimization checkpoint (typically 7-14 days).
- Optimization cadence -- Define weekly/biweekly optimization actions: bid adjustments, audience refinements, creative refreshes, budget reallocation.
Campaign Audit Process
- Account structure review -- Assess campaign organization, naming conventions, and segmentation logic.
- Audience overlap analysis -- Check for audience fragmentation or cannibalization across campaigns.
- Bid strategy assessment -- Evaluate whether current bid strategies match conversion volume and goals.
- Creative performance -- Identify top/bottom performers, creative fatigue signals, and testing gaps.
- Budget efficiency -- Analyze spend distribution vs performance distribution. Flag underspending winners and overspending losers.
- Tracking audit -- Verify conversion tracking accuracy, attribution consistency, and data freshness.
Reference Files
google-ads.md-- Google Ads campaign types, settings, optimization tactics, and platform-specific featuresmeta-ads.md-- Meta Ads campaign structures, Advantage+ configurations, creative specs, and iOS ATT strategieslinkedin-ads.md-- LinkedIn Ads targeting options, ABM strategies, lead gen optimization, and B2B-specific tacticstiktok-ads.md-- TikTok Ads creative best practices, Spark Ads setup, TikTok Shop integration, and audience strategiesprogrammatic.md-- DSP selection criteria, CTV planning, DOOH strategies, and programmatic deal typesbid-strategy.md-- Bid strategy decision trees, learning phase management, and portfolio strategy configurationsretail-media-networks.md-- Platform-specific setup for Amazon, Walmart, Target, Kroger, and Instacart advertisingmicrosoft-ads.md-- Microsoft Advertising campaign guide: Search Network reach (Bing, Yahoo, AOL, DuckDuckGo), Microsoft Audience Network, and lower-CPC opportunities vs Googleretargeting-audiences.md-- Retargeting and remarketing audience taxonomy: segment definitions, intent levels, and recommended membership windowsmedia-planning.md-- Media planning fundamentals: reach, frequency, GRP/TRP metrics, cross-channel budget allocation, and scheduling strategiesnative-advertising.md-- Native ad network landscape (Taboola, Outbrain, Nativo, and more), content discovery campaigns, and in-feed creative best practicesaudio-programmatic.md-- Digital audio advertising across streaming platforms (Spotify, Pandora/SiriusXM, iHeartRadio) and podcasts, ad models, and buying pathsads-in-ai-answers.md-- ChatGPT Ads (Advertiser/Bulk APIs, Pixel + Conversions API dedup, Custom Audiences, Product + Delta Feeds, Reporting API windows) and Google AI Mode ads via AI Max / Performance Max, with primary vs secondary sourcing marked (checked 2026-10-04)
Output Formats
- Campaign plan: Structured document with campaign hierarchy, audience definitions, bid strategies, budget allocation, creative briefs, and KPI targets
- Platform audit: Scorecard with findings, severity ratings, and prioritized action items
- Budget allocation model: Spreadsheet-ready breakdown of spend by platform, campaign, and funnel stage with projected outcomes
- Creative brief: Per-ad-format briefs with messaging angles, CTA options, and spec requirements
- Optimization playbook: Weekly/monthly checklist of optimization actions with decision criteria
Edge Cases
iOS ATT Impact on Meta Targeting
Post-iOS 14.5, Meta audience sizes shrunk and attribution windows shortened. When working with Meta campaigns, default to broader targeting with Advantage+ audience expansion, use Conversions API (CAPI) alongside the pixel, recommend 7-day click attribution, and set expectations that reported ROAS will undercount actual performance by 15-30%.
Performance Max Cannibalizing Brand Search
PMax campaigns frequently capture branded search traffic, inflating their reported performance. Always recommend running a brand exclusion list in PMax, maintaining a separate brand search campaign, and comparing incrementality by analyzing total account performance rather than PMax in isolation.
LinkedIn High CPC Management
LinkedIn CPCs are typically 3-10x higher than other platforms. Compensate by focusing on lead quality over volume, using lead gen forms (higher conversion rate than landing pages), tightening audience targeting to reduce waste, and evaluating on cost-per-qualified-lead rather than CPC.
TikTok Creative Fatigue
TikTok ad creative typically fatigues in 3-7 days. Build creative refresh cadences into every TikTok campaign plan. Recommend 3-5 active creatives per ad group with new batches produced weekly. Use Spark Ads (boosted organic) to extend creative life since they feel less like ads.
Retail Media Incrementality
Retail media ads often capture purchases that would have happened organically. When auditing retail media, question whether sales are truly incremental. Recommend running incrementality tests (holdout groups), analyzing new-to-brand metrics (Amazon provides this), and comparing organic rank changes during ad pauses.
Small Budget Cross-Platform Allocation
When total monthly budget is under $5,000, do not spread across multiple platforms. Recommend concentrating on one primary platform that best matches the audience and objective. Only expand to a second platform after the first is optimized and hitting diminishing returns.
Regulated Industry Restrictions
Healthcare, finance, alcohol, cannabis, gambling, and political advertising face platform-specific restrictions. Always check platform policies before recommending campaign types. Some platforms ban certain industries entirely (TikTok restricts financial services ads in some markets). Reference platform-specific docs for current restriction lists.
Related Skills
- CRO -- Landing page and conversion optimization for ad traffic destinations
- Analytics & Insights -- Attribution modeling, conversion tracking setup, and performance analysis
- Audience Intelligence -- Deep audience research to inform targeting strategies
- Content Engine -- Ad creative copywriting and messaging frameworks
- Funnel Architect -- Full-funnel strategy that paid advertising plugs into
- Emerging Channels -- Social commerce and newer ad platforms (TikTok Shop, CTV)
© indranilbanerjee, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 13 other files in skills/paid-advertising of indranilbanerjee/digital-marketing-pro.
- SKILL.md
- ads-in-ai-answers.md
- audio-programmatic.md
- bid-strategy.md
- google-ads.md
- linkedin-ads.md
- media-planning.md
- meta-ads.md
- microsoft-ads.md
- native-advertising.md
- programmatic.md
- retail-media-networks.md
- retargeting-audiences.md
- tiktok-ads.md
Open the folder on GitHubat commit 9e949f3
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in indranilbanerjee/digital-marketing-pro, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Paid Advertising next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Paid Advertising this skillindranilbanerjee/digital-marketing-pro | 862 | 1 repos | ~5.3k | Automated safety check: Pass | MIT | |
| Ad CreativeLeoYeAI/openclaw-marketing-skills | 1k | 8 repos | ~3.4k | Automated safety check: Pass | Custom licence | |
| Blog GoogleAgriciDaniel/claude-blog | 2.3k | 1 repos | ~3.3k | Automated safety check: Notes | MIT | |
| Ad Account Auditoraaron-he-zhu/aaron-marketing-skills | 2.9k | 2 repos | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Ad Creative Builderaaron-he-zhu/aaron-marketing-skills | 2.9k | 2 repos | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Ad Test Designeraaron-he-zhu/aaron-marketing-skills | 2.9k | 2 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Blog Google
AgriciDaniel/claude-blog
Google API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity…
Ad Account Auditor
aaron-he-zhu/aaron-marketing-skills
A skill your agent uses when auditing a paid ad account for incremental contribution, wasted spend, or measurement integrity before scaling; runs a typed 20-item ROAS profile with verified vetoes…
Ad Creative Builder
aaron-he-zhu/aaron-marketing-skills
A skill your agent uses when the user asks to "write ad copy", "generate RSA headlines", or "build ad creative at volume"; produces ad units — RSA headlines/descriptions, hooks, and an angle matrix…
Ad Test Designer
aaron-he-zhu/aaron-marketing-skills
A skill your agent uses when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"…
Paid Ads Audit
AgriciDaniel/claude-ads
Runs a source-grounded paid advertising audit across up to 12 ad platforms, with parallel platform workers, deterministic scoring and a versioned JSON bundle.
More from indranilbanerjee/digital-marketing-pro
All 162 skills in this repoImport Template
indranilbanerjee/digital-marketing-pro
Import a deliverable template as a reusable placeholder template per brand.
Ab Test Plan
indranilbanerjee/digital-marketing-pro
Plan an A/B test by script: sample size per variant, days to run, stopping rules.
Aeo Audit
indranilbanerjee/digital-marketing-pro
Run a one-time AEO audit of six AI answer engines, scored per surface.
Agent Readiness Audit
indranilbanerjee/digital-marketing-pro
Audit agent readiness by script: AI-crawler rules, product schema, no-JS HTML, feeds.
Backlink Gap
indranilbanerjee/digital-marketing-pro
Find backlink gap domains linking to competitors, not you, scored by script.
C2pa Metadata
indranilbanerjee/digital-marketing-pro
Embed C2PA provenance in AI-generated images, video or PDF by script.
Related
Categories
Questions about Paid Advertising
What does Paid Advertising do?
Plan or audit paid ads with current platform rules and benchmarks: Google PMax/AI Max, Meta, retail. Paid Advertising is an agent skill from indranilbanerjee/digital-marketing-pro. Plan or audit paid ads with current platform rules and benchmarks: Google PMax/AI Max, Meta, retail.
When should I use Paid Advertising?
Paid Advertising fits situations like: tasks that involve Paid advertising.
How do I install Paid Advertising in Claude Code?
Run `npx skills add indranilbanerjee/digital-marketing-pro --skill paid-advertising -a claude-code`. Or copy the skill folder (skills/paid-advertising in indranilbanerjee/digital-marketing-pro) into .claude/skills/paid-advertising in your project. Claude Code loads it when a task matches its description.
How do I install Paid Advertising in Codex?
Run `npx skills add indranilbanerjee/digital-marketing-pro --skill paid-advertising -a codex`. Or copy the skill folder (skills/paid-advertising in indranilbanerjee/digital-marketing-pro) into .agents/skills/paid-advertising in your project. Codex loads it when a task matches its description.
Can I use Paid Advertising in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add indranilbanerjee/digital-marketing-pro --skill paid-advertising -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paid-advertising, .gemini/skills/paid-advertising, .github/skills/paid-advertising and .opencode/skills/paid-advertising in your project.
What does Paid Advertising need to run?
Going by SKILL.md and its folder, Paid Advertising needs the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Paid Advertising access the network?
SKILL.md names 7 domains. As links in the text: blog.google, support.google.com, learn.microsoft.com, advertising.amazon.com, developers.openai.com, developers.google.com and ads-developers.googleblog.com. This is read from the text; nothing was executed.
Is Paid Advertising safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Paid Advertising use?
Paid Advertising is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Paid Advertising use?
About 5.3k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Paid Advertising?
Skills that share tags, products or a category with Paid Advertising: Ad Creative (LeoYeAI/openclaw-marketing-skills, 1k stars), Blog Google (AgriciDaniel/claude-blog, 2.3k stars), Ad Account Auditor (aaron-he-zhu/aaron-marketing-skills, 2.9k stars) and Ad Creative Builder (aaron-he-zhu/aaron-marketing-skills, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Paid Advertising?
indranilbanerjee (a GitHub user) maintains it in indranilbanerjee/digital-marketing-pro, which has 862 GitHub stars. The repository holds 162 skills in this directory. The repository was last updated on October 9, 2026.
Source: indranilbanerjee/digital-marketing-pro on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.